Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks
Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a coarse map of salient features in an image, which rarely tells the whole story of what a convolutional neural network (CNN) learned. Using COVID-19 chest X-rays, we present a method for interpreting what a CNN has learned by utilizing Generative Adversarial Networks (GANs). Our GAN framework disentangles lung structure from COVID-19 features. Using this GAN, we can visualize the transition of a pair of COVID negative lungs in a chest radiograph to a COVID positive pair by interpolating in the latent space of the GAN, which provides fine-grained visualization of how the CNN responds to varying features within the lungs.
Code (1)
Similar Papers 제목 키워드 기반
Counterfactual Explanations via Riemannian Latent Space Traversal
The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for providing actionable explanations to pra…
counterfactualCounterfactual ExplanationDecoderChemoVerse: Manifold traversal of latent spaces for novel molecule discovery
In order to design a more potent and effective chemical entity, it is essential to identify molecular structures with the desired chemical properties. Recent advances in generative models using neural networks and machin…
Heuristic SearchTowards Visually Explaining Variational Autoencoders
Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have…
DisentanglementQUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations
Deep Neural Networks (DNNs) stand out as one of the most prominent approaches within the Machine Learning (ML) domain. The efficacy of DNNs has surged alongside recent increases in computational capacity, allowing these …
counterfactualExplainable ModelsInterpretable ECG classification via a query-based latent space traversal (qLST)
Electrocardiography (ECG) is an effective and non-invasive diagnostic tool that measures the electrical activity of the heart. Interpretation of ECG signals to detect various abnormalities is a challenging task that requ…
DiagnosticECG ClassificationElectrocardiography (ECG)